FarsBase, a Farsi Knowledge Graph, consists of more than 500K of entities and 7 million relations between them. Data (triple) have been extracted from Farsi edition of Wikipedia and raw text using NLP techniques. According to the semantic web, RDF data model and OWL2 ontology have been employed to implement the Farsi Knowledge Graph (FKG). Resources and their relations are stored in triple format, therefore, access to the knowledge graph is provided by a SPARQL endpoint. The project is aimed to improve results of Farsi search engines so that a search system has been developed on the FarsBase. An ontology,
retrieved from DBpedia ontology, was created based on resources of Farsi Wikipedia. Moreover, more than 8000 templates and properties of Wikipedia have been mapped to the ontology automatically and manually. Furthermore, a part of the ontology has been mapped to the FarsNet, the Persian WordNet, for research purposes.
In order to achieve high performance and flexible data model, a two-level architecture for storing
data was designed to separate data from metadata.
FarsBase is available in farsbase.net.